Maria Rubiston.M currently Pursuing Ph.D in Electronics and Communication Engineering from
Anna University,Chennai-25, received his M.Tech in VLSI Design from Sathyabama University, Chennai
-119 in 2013 and completed B.E-Electronics and Communication Engineering in 2010 from Madha
Engineering College, Affiliated to Anna University, Chennai .He is currently working as Assistant
Professor Faculty of Electronics and Communication Engineering, Ramco Institute of Technology,
Rajapalayam. Has a total teaching experience of 11.5 years in Engineering colleges 2.5 years in Industry.
His area of Interest is VLSI Signal Processing, Wireless Sensor Networks, Deep Learning. He has
published 7 patents and Received Event Grants from SERB,ICMR & BRNS for conducting workshops.
He has published many papers in various reputed National and International journals. He has hands on
experience with modern tools Cadence Virtuoso, Xilinx Vivado, MATLAB, Tanner EDA.
EDUCATION
M.Tech.,
RESEARCH, TEACHING, or OTHER INTERESTS
Engineering, Hardware and Architecture, Artificial Intelligence, Multidisciplinary
Evolution-based Deployment with Efficient Routing and Crow Search Optimization in Internet of Things Application C. Kalaivanan, Ayman Amer, Maria Rubiston. M, M. Vennila, Jayant Giri, M. Dinesh Proceedings of the International Conference on Intelligent Computing and Control Systems Iciccs 2025, 2025 IoT technologies to bolster residential security, safety, and sustainability. By leveraging facial recognition for door access, enhancing fire safety monitoring, and integrating energy harvesting, it aims to create more resilient and eco-friendly residential environments. These innovations offer comprehensive solutions to address evolving challenges and optimize residential living. An ED Model coupled with Crow Search Optimization (CSO) for enhancing the efficiency and reliability of IoT applications. The ED model integrates static routing mechanisms with efficient protocols like AOMDV, ensuring robust connectivity and energy-efficient operation in diverse environments. Leveraging CSO, inspired by collective crow intelligence, enhances network performance by dynamically adapting to changing conditions. Through simulations and comprehensive analysis, the proposed approach demonstrates superior performance compared to existing models, achieving high data delivery ratio, network throughput, and energy efficiency. This integrated framework offers a sustainable solution for resilient IoT deployments, addressing evolving challenges and optimizing residential living environments.
Enhance Path Selection with Multi-Hop Data Dissemination to Achieve High Quality-of-Service in Vehicular Communication Y Shasikala, V. Chinnammal, Maria Rubiston. M, Imad Shalout, Prashant D. Kamble, M. Dinesh Proceedings 1st International Conference on Frontier Technologies and Solutions Icfts 2025, 2025 VANETs through the proposed EPMHQ approach. It discusses the challenges of VANETs, and related works, and introduces the EPMHQ approach integrating DSRC, IEEE 802.11p, AODV routing, and Whale Optimization Algorithm (WOA) based path selection. The methodology and objectives of the approach are outlined, emphasizing its aim to enhance network performance and efficiency. Results from experiments utilizing NS-2 simulation are shown, indicating better performance in packet delivery ratio, network throughput, average delay, energy efficiency, and routing overhead when compared to current techniques. The abstract concludes by highlighting the potential of the EPMHQ approach in improving VANETs for intelligent transportation systems.
An Improved Bat Optimization Algorithm for Knowledge Discovery for Routing and Energy Efficiency in the Internet of Things Environment Ramachandran R, L. Kannagi, Maria Rubiston. M, Govindaraj Karthikeyan, R. Ratheesh, Abijith G R Proceedings of the 2024 International Conference on Innovative Computing Intelligent Communication and Smart Electrical Systems Icses 2024, 2024 An improved optimization algorithm, IBA, enhances routing and energy efficiency in IoT environments. As energy conservation becomes increasingly vital in our technological landscape, managing resource consumption is crucial for sustainability. The Internet of Things (IoT) has revolutionized connectivity, enabling diverse applications across various sectors, from smart homes to industrial systems. The impending 5G technology promises to accelerate this transformation further, offering unprecedented speed and coverage. However, with the exponential growth in mobile data transmission, network operators face the challenge of meeting escalating demands. Bio-inspired optimization techniques, like the Bat Algorithm (BA), have emerged as promising solutions due to their computational efficiency and applicability to IoT challenges. The proposed IBA builds upon BA principles, introducing novel enhancements to address specific limitations. Through methodical testing, IBA shows better results in packet delivery ratio, network throughput, energy efficiency, average delay, and routing overhead than current protocols. These findings highlight the capability of optimized algorithms to improve IoT system performance and address changing application needs.
An Effective Cluster Based Energy and Power Optimization Routing Protocol Design over Wireless Sensor Network Environment SK. Sheema, A. Vanathi, Maria Rubiston. M, W. T. Chembian, N. Kalaiarasi, ATA. Kishore Kumar Proceedings of the 2024 International Conference on Innovative Computing Intelligent Communication and Smart Electrical Systems Icses 2024, 2024 Environmental monitoring, industrial automation, and smart communities are among the numerous applications in which Wireless Sensor Networks (WSN) are essential. Nevertheless, the effective management of energy and power resources continues to be a substantial obstacle, as sensor nodes are frequently deployed in large quantities and are battery-powered. This paper introduces the Power Optimized Routing Protocol (PORP), a novel cluster-based routing protocol that is intended to optimize energy and power consumption in WSN. The proposed scheme's efficacy is evaluated by cross-validating it with the conventional routing protocol, Dynamic Source Routing (DSR). The dynamic clustering mechanism that has been proposed in our protocol, PORP, minimizes energy consumption through intelligent methods of cluster formation and data aggregation. In this way, it further extends the network's lifecycle and reduces its average energy usage through energy-efficient and power-aware algorithms. We evaluated the effectiveness of our protocol through comprehensive simulation and compared our protocol with existing ones regarding energy efficiency, network lifetime, and data transmission reliability. The study proved to be very in-depth and comprehensive regarding the efficiency of the protocol, which highlighted the possibilities of the protocol's implementation with real-world WSN applications to ensure proper functioning of even more sustainable and efficient wireless sensor networks.
Experimental Analysis of Artificial Intelligence Powered Adaptive Learning Methodology Using Enhanced Deep Learning Principle K.M. Rayudu, V. Chinnammal, M Maria Rubiston., P. Padmaloshani, R. Singaravelu, N.R Gladiss Merlin Proceedings of the 2024 International Conference on Innovative Computing Intelligent Communication and Smart Electrical Systems Icses 2024, 2024 The rapid advancement of deep learning technologies and Artificial Intelligence (AI) has facilitated the development of sophisticated adaptive learning methodologies. The experimental analysis presented in this manuscript is of a novel adaptive learning methodology propelled by AI, known as the Learning Assisted Power Adaptive Strategy (LPAS). This approach optimizes the learning process in dynamic environments by combining adaptive learning techniques with sophisticated deep learning architectures. The accuracy levels of the proposed scheme are tested by cross-validating it with the traditional learning scheme called Recurrent Neural Network (RNN) so that complex and time-varying data patterns can be handled effectively. The Learning Assisted Power Adaptive Strategy is anticipated to enhance its fitness to make accurate predictions and encourage individual learning with adaptability over new and changing circumstances. The LPAS performance is assessed against a variety of benchmarks, such as precision, recall, specificity and sensitivity, through a succession of controlled experiments. The model's adaptive capabilities also enabled a more responsive response to data fluctuations, thereby improving its overall robustness. This research provides valuable insights for future advancements in the field and contributes to the continual growth of AI-driven educational resources and adaptive platforms.
An Image Oriented AI Methodology to Detect Animal Footprints Based on Enhanced Neural Optimization and Classification Scheme R. Manasa, A. Balaji, Maria Rubiston. M, S. Kavitha, V. Lavanya, Ata. Kishore Kumar Proceedings of the 2024 International Conference on Innovative Computing Intelligent Communication and Smart Electrical Systems Icses 2024, 2024 The identification and detection of animal footprints are essential for the conservation of wildlife, ecological studies, and wildlife monitoring. This paper introduces a novel method for detecting animal footprints that combines deep learning and image processing. The approach, known as the Enhanced Neural Optimization and Classification Scheme (ENOCS), is cross-validated with the conventional model, the Support Vector Machine (SVM), to assess the efficacy of the proposed scheme. Our approach employs a learning model that has been fined-tuned on a dataset of various types of animal print to extract and classify features with high accuracy. The quality of the input data is enhanced through the image-processing component by eliminating noise, normalizing illumination, and performing morphological operations to draw emphasis to footprint patterns. Performance metrics are tested on a benchmark dataset containing a wide range of animal traces and evaluated with conventional image recognition methods. The results indicate that our method attains significant improvement in accuracy relative to the state-of-the-art technique, known as SVM. Furthermore, our approach is invariant to variations in environmental conditions and image quality. The proposed scheme thus provides a reliable and effective tool to identify animal imprints, thereby increasing the effectiveness of measures for ecosystems and conservation.
Vehicle Speed Determination Using Haarcascade Algorithm M. Maria Rubiston, Harigaran K, Darshini S, Mukeshkumar B, Santhosh U, Albee Micheal J IEEE 9th International Conference on Smart Structures and Systems Icsss 2023, 2023 The model will combine the wheel speed and satellite communication information to calculate the impact of road navigation on the IMU and its horizontal speed compared to average wheel speeds and wheel Speed Department (CRT) information. A longitudinal vehicle speed estimator using triangulation is generated from tests conducted by participants, consisting of three virtual sensors that build synthetic longitudinal speed tracks by combining multiple data points. The speed estimation is being evaluated in a detailed and analytical way under a variety of driving scenarios under the testing hardware-in-the-loop tests. The error is less than 10%.
